SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks

Abstract

This paper introduces SpotV2Net, a multivariate intraday spot volatility forecasting model based on a Graph Attention Network architecture. SpotV2Net represents assets as nodes within a graph and includes non-parametric high-frequency Fourier estimates of the spot volatility and co-volatility as node features. Further, it incorporates Fourier estimates of the spot volatility of volatility and co-volatility of volatility as features for node edges, to capture spillover effects. We test the forecasting accuracy of SpotV2Net in an extensive empirical exercise, conducted with the components of the Dow Jones Industrial Average index. The results we obtain suggest that SpotV2Net yields statistically significant gains in forecasting accuracy, for both single-step and multi-step forecasts, compared to a panel heterogenous auto-regressive model and alternative machine-learning models. To interpret the forecasts produced by SpotV2Net, we employ GNNExplainer \citep{ying2019gnnexplainer}, a model-agnostic interpretability tool, and thereby uncover subgraphs that are critical to a node's predictions.

arXiv comment33 pages, 5 figures. Accepted on the International Journal of Forecasting

References in corpus (11)

• XGBoost: A Scalable Tree Boosting System
• A Comprehensive Survey on Graph Neural Networks
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Graph Neural Network for Traffic Forecasting: A Survey
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better
• A Fourier transform method for nonparametric estimation of multivariate volatility
• HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
• Multi-Behavior Graph Neural Networks for Recommender System
• Multivariate Realized Volatility Forecasting with Graph Neural Network
• Discovering Supply Chain Links with Augmented Intelligence